> >
> > Some PMDs can only support digest being
> > encrypted separately in auth-cipher operations.
> > Thus it is required to add feature flag in PMD to reflect if it does support
> > digest-appended
> > both: digest generation with encryption and decryption with digest
> > verification.
> > Th
03/04/2019 12:32, Lukasz Krakowiak:
> Lukasz Krakowiak (3):
> test: rename test_power_acpi_cpufreq.c ->
> app/test/test_power_cpufreq.c
> test: remove prefix _acpi from UT power function/test names
> test: add UT for power turbo feature
I decided to squash first 2 patches and apply,
even
This patch adds extra features to the compress performance
test. Some important parameters (memory allocation,
number of ops, number of segments) are calculated and
printed out on the screen.
Signed-off-by: Artur Trybula
---
.../comp_perf_test_common.c | 93 ++-
v2 changes:
- merged with the series "add multiple cores feature to
test-compress-perf"
- function renamed: print_report_header() -> print_test_dynamics()
v3 changes:
- commented code removed
This patch depends on the series "add multiple cores feature to
> -Original Message-
> From: Neil Horman
> Sent: Tuesday, June 18, 2019 12:44 AM
> To: Jerin Jacob Kollanukkaran
> Cc: dev@dpdk.org; Bruce Richardson ;
> Thomas Monjalon
> Subject: [EXT] Re: [PATCH v2 09/10] octeonx: mark internal functions with
> __rte_internal
>
> On Mon, Jun 17, 2019
Hi Souvik,
I am also facing this issue on DPDK 17.11.4 but not sure whether it is
because of fragmented traffic or not.
Are you able to get the direction regarding this issue? Can you please
guide.
Thanks,
Chetan Bhasin
On Sat, Jun 15, 2019 at 12:00 AM Dey, Souvik wrote:
> Hi All,
>
On Thu, Jul 4, 2019 at 7:14 PM Stephen Hemminger
wrote:
> On Fri, 14 Jun 2019 11:39:17 +0200
> David Marchand wrote:
>
> > /* Supports only RTE_KDRV_NIC_UIO */
> > + if (pdev->kdrv != RTE_KDRV_NIC_UIO)
> > + RTE_LOG(DEBUG, EAL, "Unsupported kernel driver? Defaulting
> to IO
On Sun, Mar 31, 2019 at 12:57 AM Thomas Monjalon
wrote:
> 13/03/2019 18:06, Natanael Copa:
> > A set of patches to fix build with musl libc. I also did a few cleanups
> wrt
> > macros and fixed a few scary compiler warnings while at it.
> >
> > Please note that those are only compile tested on x8
On 07-Jun-19 3:28 AM, Takeshi Yoshimura wrote:
sPAPR allows only page_shift from VFIO_IOMMU_SPAPR_TCE_GET_INFO ioctl.
However, Linux 4.17 or before returns incorrect page_shift for Power9.
I added the code for retrying creation of sPAPR DMA window.
Signed-off-by: Takeshi Yoshimura
---
This do
04/07/2019 19:14, Stephen Hemminger:
> On Fri, 14 Jun 2019 11:39:17 +0200
> David Marchand wrote:
>
> > /* Supports only RTE_KDRV_NIC_UIO */
> > + if (pdev->kdrv != RTE_KDRV_NIC_UIO)
> > + RTE_LOG(DEBUG, EAL, "Unsupported kernel driver? Defaulting to
> > IOVA as 'PA'\n");
>
> Ma
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Thursday, July 4, 2019 5:53 PM
> To: Sunil Kumar Kori
> Cc: dev@dpdk.org; Ananyev, Konstantin ;
> jer...@marvell.com
> Subject: Re: [dpdk-dev] [PATCH v2 1/3] lib/librte_ip_frag: Remove
> PKT_TX_IP_CKSUM
From: Jerin Jacob
This patchset adds support for OCTEON TX2 DMA driver as DPDK rawdevice.
v2:
# Moved maintainers file to the first patch
# removed reference to to v19.05
# Makefile/Meson CFLAGS moved to specific patches
# Squshed Documentation updates to specific patches
# Sync with Bruce's us
From: Jerin Jacob
Add the make and meson based build infrastructure along
with the DMA device probe with documentation infrastructure.
Signed-off-by: Jerin Jacob
Signed-off-by: Satha Rao
Signed-off-by: Vamsi Attunuru
---
MAINTAINERS | 6 ++
config/common_ba
From: Satha Rao
Probe function enhanced to allocate and initialize PMD private data.
Signed-off-by: Satha Rao
Signed-off-by: Vamsi Attunuru
---
drivers/raw/octeontx2_dma/otx2_dpi_rawdev.c | 25 +++--
drivers/raw/octeontx2_dma/otx2_dpi_rawdev.h | 56 +
2 files changed,
From: Satha Rao
Register dev_configure API to configure DPI PCI devices.
After successful initialization send message to PF to open
corresponding DPI DMA queue. At present hardware doesn't
support mail box for DPI, so PMD to PF communication uses
pre build kernel devfs.
Signed-off-by: Satha Rao
From: Satha Rao
Add dequeue, device start, stop, close and reset operations.
Signed-off-by: Satha Rao
Signed-off-by: Vamsi Attunuru
---
drivers/raw/octeontx2_dma/otx2_dpi_rawdev.c | 64 +
1 file changed, 64 insertions(+)
diff --git a/drivers/raw/octeontx2_dma/otx2_dpi_raw
From: Satha Rao
Send message to PF to stop DMA queue when device close is
called from application.
Defined the required data structures to support enqueue and
dequeue APIs.
Signed-off-by: Satha Rao
Signed-off-by: Vamsi Attunuru
---
drivers/raw/octeontx2_dma/otx2_dpi_rawdev.c | 33 +
driv
From: Satha Rao
Add enqueue operation.
Signed-off-by: Satha Rao
Signed-off-by: Vamsi Attunuru
---
doc/guides/rawdevs/octeontx2_dma.rst| 6 +
drivers/raw/octeontx2_dma/otx2_dpi_rawdev.c | 166
2 files changed, 172 insertions(+)
diff --git a/doc/guides/rawdevs/oc
From: Satha Rao
Sample test to verify DMA functionality, this test covers
internal transfer mode.
Signed-off-by: Satha Rao
Signed-off-by: Vamsi Attunuru
---
doc/guides/rawdevs/octeontx2_dma.rst| 14 ++
drivers/raw/octeontx2_dma/Makefile | 3 +-
drivers/raw/octeontx2_dma/me
From: Jerin Jacob
Update the devbind script with new section of DMA devices, also
added OCTEONTX2 DMA device ID to DMA device list
Signed-off-by: Jerin Jacob
Signed-off-by: Satha Rao
---
doc/guides/rawdevs/octeontx2_dma.rst | 11 +++
usertools/dpdk-devbind.py| 4 +++-
2 f
On Fri, Jul 05, 2019 at 10:14:42AM +0800, Xiaoyu Min wrote:
> Add new rte_flow_item_gre_key in order to match the optional key field.
>
> Acked-by: Ori Kam
> Signed-off-by: Xiaoyu Min
Acked-by: Adrien Mazarguil
--
Adrien Mazarguil
6WIND
02/07/2019 02:27, Honnappa Nagarahalli:
> Reset tbl_rwc_test_param to discard data from previous run
> of the test.
>
> Fixes: c7eb0972e74b ("test/hash: add lock-free r/w concurrency")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Honnappa Nagarahalli
> Reviewed-by: Dharmik Thakkar
Series applied,
Hi Jin,
On 6/26/19 6:38 PM, JinYu wrote:
This patch introduces two new messages VHOST_USER_GET_INFLIGHT_FD
and VHOST_USER_SET_INFLIGHT_FD to support transferring a shared
buffer between qemu and backend.
Firstly, qemu uses VHOST_USER_GET_INFLIGHT_FD to get the
shared buffer from backend. Then q
04/07/2019 18:27, Bruce Richardson:
> On Thu, Jul 04, 2019 at 05:36:08PM +0200, Timothy Redaelli wrote:
> > The action for timer_secondary_spawn_wait should be enabled only when
> > CONFIG_RTE_LIBRTE_TIMER is enabled.
> >
> > Fixes: 50247fe03fe0 ("test/timer: exercise new APIs in secondary process
On 16-Apr-19 4:43 AM, ogawa.yasuf...@lab.ntt.co.jp wrote:
From: Yasufumi Ogawa
In secondary_msl_create_walk(), it creates a file for fbarrays with its
PID for reserving unique name among secondary processes. However, it
does not work if secondary is run as app container because each of
containe
>
> 03/07/2019 20:31, Chautru, Nicolas:
> > Thomas wrote:
> > >> Nicolas Chautru (7):
> > >> bbdev: renaming non-generic LTE specific structure
> > >> bbdev: extension of BBDEV API for 5G FEC
> > >> docs/guides: updating bbdev API for 5GNR operations
> > >> baseband/turbo_sw: extension
On Fri, Jul 05, 2019 at 10:14:45AM +0800, Xiaoyu Min wrote:
> support matching on GRE key and present bits (C,K,S)
>
> example testpmd command could be:
> testpmd>flow create 0 ingress group 1 pattern eth / ipv4 /
> gre / gre_key value is 0x12345678 / end
> actions rss queues 1 0
05/07/2019 06:26, pbhagavat...@marvell.com:
> From: Pavan Nikhilesh
>
> The ARMv8.1 CASP instruction works with even register pairs and since
> there no register constraint in older versions of GCC/Clang, use
> explicit register allocation to satisfy CASP requirements.
> Remove function level opt
On Thu, Jun 20, 2019 at 10:07:12PM +0200, Maxime Coquelin wrote:
> Having this info logged by default when analysing bug reports
> has proved to be useful.
>
> Signed-off-by: Maxime Coquelin
> ---
> lib/librte_vhost/vhost_user.c | 5 +
> 1 file changed, 5 insertions(+)
Applied to dpdk-next-
On Fri, 19-07-05, 10:58, Adrien Mazarguil wrote:
> On Fri, Jul 05, 2019 at 10:14:45AM +0800, Xiaoyu Min wrote:
> > support matching on GRE key and present bits (C,K,S)
> >
> > example testpmd command could be:
> > testpmd>flow create 0 ingress group 1 pattern eth / ipv4 /
> > gre / gre_key
Fixes: 552afc420a67 ("mem: add contig walk function")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
---
lib/librte_eal/common/include/rte_memory.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/librte_eal/common/include/rte_memory.h
b/lib/librte_eal/common/include/r
Following empirical tries, this test wants at least 3300M of memory to
run.
Signed-off-by: David Marchand
---
app/test/test_table.c | 7 +++
1 file changed, 7 insertions(+)
diff --git a/app/test/test_table.c b/app/test/test_table.c
index a4b0ed6..dca1b33 100644
--- a/app/test/test_table.c
+
The names of the rawdev drivers and the resultant libraries they built
were pretty inconsistent. In terms of directory names, some had "rawdev"
in the name, e.g. skeleton_rawdev, ifpga_rawdev, while others didn't.
Also, for the built .so/.a libraries, the names were not always
consistent between ma
The driver names for rawdevs were both different in make and meson builds
and were non-standard in the make version in that some included "rawdev" in
the name while others didn't.
Therefore, for global consistency of naming, we can use "rte_rawdev" rather
than "rte_pmd" for the prefix for the libr
The ifpga and skeleton rawdev drivers included "rawdev" in their directory
names, which was superfluous given that they were in the drivers/raw
directory. Shorten the names via this patch.
For meson builds, this will rename the final library .so/.a files
produced, but those will be renamed again l
On 19-07-04 19:59, Ferruh Yigit wrote:
> External Email
>
> --
> On 7/4/2019 3:39 PM, kka...@marvell.com wrote:
> > From: Krzysztof Kanas
> >
> > Print system error to make easier diagnosis of errors with af_packet.
> >
> > Sig
On Fri, Jul 05, 2019 at 10:33:59AM +0100, Bruce Richardson wrote:
> The names of the rawdev drivers and the resultant libraries they built
> were pretty inconsistent. In terms of directory names, some had "rawdev"
> in the name, e.g. skeleton_rawdev, ifpga_rawdev, while others didn't.
> Also, for t
05/07/2019 11:35, Bruce Richardson:
> On Fri, Jul 05, 2019 at 10:33:59AM +0100, Bruce Richardson wrote:
> > The names of the rawdev drivers and the resultant libraries they built
> > were pretty inconsistent. In terms of directory names, some had "rawdev"
> > in the name, e.g. skeleton_rawdev, ifpg
05/07/2019 11:38, Thomas Monjalon:
> 05/07/2019 11:35, Bruce Richardson:
> > On Fri, Jul 05, 2019 at 10:33:59AM +0100, Bruce Richardson wrote:
> > > The names of the rawdev drivers and the resultant libraries they built
> > > were pretty inconsistent. In terms of directory names, some had "rawdev"
On 05-Jul-19 10:18 AM, David Marchand wrote:
Fixes: 552afc420a67 ("mem: add contig walk function")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
---
Acked-by: Anatoly Burakov
--
Thanks,
Anatoly
> -Original Message-
> From: dev On Behalf Of Artur Trybula
> Sent: Wednesday, July 3, 2019 8:54 PM
> To: dev@dpdk.org; fiona.tr...@intel.com; akhil.go...@nxp.com;
> adamx.dybkow...@intel.com; arturx.tryb...@intel.com;
> tjozwia...@gmail.com
> Subject: [dpdk-dev] [PATCH v6 0/6] add mult
This series patchs are based on RFC [1], which enable the matching on
GRE's key field.
And enabled MLX5 device supports on this.
[1] https://patches.dpdk.org/patch/53432/
---
v2:
* remove struct rte_flow_item_gre_key in order to comply new convention
v3:
* updated release note
* fixed one b
Add new rte_flow_item_gre_key in order to match the optional key field.
Acked-by: Ori Kam
Acked-by: Adrien Mazarguil
Signed-off-by: Xiaoyu Min
---
doc/guides/prog_guide/rte_flow.rst | 9 +
lib/librte_ethdev/rte_flow.c | 1 +
lib/librte_ethdev/rte_flow.h | 13 +
support matching on the present bits (C,K,S)
as well as the optional key field.
If the rte_flow_item_gre_key is specified in pattern,
it will set K present match automatically.
Signed-off-by: Xiaoyu Min
---
doc/guides/rel_notes/release_19_08.rst | 5 ++
drivers/net/mlx5/mlx5_flow.c |
DR engine support matching on GRE protocol field without MPLS supports.
So bypassing the MPLS check when DR is enabled.
Signed-off-by: Xiaoyu Min
---
drivers/net/mlx5/mlx5_flow.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/mlx5/mlx5_flow.c b/drivers/net/mlx5/mlx5_flow.c
ind
support matching on GRE key and present bits (C,K,S)
example testpmd command could be:
testpmd>flow create 0 ingress group 1 pattern eth / ipv4 /
gre / gre_key value is 0x12345678 / end
actions rss queues 1 0 end / mark id 196 / end
Which will match GRE packet with k present
If there are multiple threads contending, they all attempt to take the
spinlock lock at the same time once it is released. This results in a
huge amount of processor bus traffic, which is a huge performance
killer. Thus, if we somehow order the lock-takers so that they know who
is next in line for
Let all architectures use generic MCS queued lock implementation.
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
Reviewed-by: Honnappa Nagarahalli
---
.../common/include/arch/arm/rte_mcslock.h | 23 ++
.../common/include/arch/ppc_64/rte_mcslock.h | 19 ++
This patch set added MCS lock library and its unit test.
The MCS lock (proposed by John M. Mellor-Crummey and Michael L. Scott) provides
scalability by spinning on a CPU/thread local variable which avoids expensive
cache bouncings. It provides fairness by maintaining a list of acquirers and
passin
Unit test and perf test for MCS queued lock.
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
Reviewed-by: Honnappa Nagarahalli
---
MAINTAINERS | 1 +
app/test/Makefile | 1 +
app/test/autotest_data.py | 6 +
app/test/autotest_test_funcs.py | 32 ++
On restarting worker 0 after shutdown, packets handled by
worker 0 must be incremented only when a packet is received by
it.
Fixes: c3eabff124e6 ("distributor: add unit tests")
Cc: sta...@dpdk.org
Signed-off-by: Harman Kalra
---
app/test/test_distributor.c | 3 ++-
1 file changed, 2 insertions(
No of workers should never exceed RTE_MAX_LCORE.
RTE_DIST_ALG_SINGLE also require no of workers check.
Fixes: 775003ad2f96 ("distributor: add new burst-capable library")
Cc: sta...@dpdk.org
Signed-off-by: Harman Kalra
---
lib/librte_distributor/rte_distributor.c | 11 ++-
1 file changed
>
> This patchset adds the ECN and DSCP tunnel mode header reconstruction
> support for rte_ipsec library. The ipsec-secgw sample application is
> updated with the feature's enabling and a python3 script for testing
> the correctness of the implementation.
>
> v7:
> - rebased on top of latest d
This patch set added MCS lock library and its unit test.
The MCS lock (proposed by John M. Mellor-Crummey and Michael L. Scott) provides
scalability by spinning on a CPU/thread local variable which avoids expensive
cache bouncings. It provides fairness by maintaining a list of acquirers and
passin
If there are multiple threads contending, they all attempt to take the
spinlock lock at the same time once it is released. This results in a
huge amount of processor bus traffic, which is a huge performance
killer. Thus, if we somehow order the lock-takers so that they know who
is next in line for
Unit test and perf test for MCS queued lock.
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
Reviewed-by: Honnappa Nagarahalli
---
MAINTAINERS | 1 +
app/test/Makefile | 1 +
app/test/autotest_data.py | 6 +
app/test/autotest_test_funcs.py | 32 ++
Let all architectures use generic MCS queued lock implementation.
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
Reviewed-by: Honnappa Nagarahalli
---
.../common/include/arch/arm/rte_mcslock.h | 23 ++
.../common/include/arch/ppc_64/rte_mcslock.h | 19 ++
Hi Stephen,
On 28/06/2019 16:35, Stephen Hemminger wrote:
On Fri, 28 Jun 2019 15:16:30 +0100
"Medvedkin, Vladimir" wrote:
Hi Honnappa,
On 28/06/2019 14:57, Honnappa Nagarahalli wrote:
Hi all,
On 28/06/2019 05:34, Stephen Hemminger wrote:
On Fri, 28 Jun 2019 02:44:54 +
"Ruifeng Wang (A
> -Original Message-
> From: Thomas Monjalon
> Sent: Friday, July 5, 2019 4:12 AM
> To: Phil Yang (Arm Technology China) ; Honnappa
> Nagarahalli
> Cc: dev@dpdk.org; jer...@marvell.com; hemant.agra...@nxp.com; Gavin
> Hu (Arm Technology China) ; nd
> Subject: Re: [dpdk-dev] [PATCH v1 0/3
From: Vamsi Attunuru
Patch fixes npa pool range errors observed while creating mempool.
During mempool creation, octeontx2 mempool driver populates pool
range fields before enqueueing the buffers. If any enqueue or dequeue
operation reaches npa hardware prior to the range field's HW context
updat
On 01/07/2019 07:44, Ruifeng Wang (Arm Technology China) wrote:
Hi Medvedkin,
-Original Message-
From: Stephen Hemminger
Sent: Friday, June 28, 2019 23:35
To: Medvedkin, Vladimir
Cc: Honnappa Nagarahalli ; Ruifeng Wang
(Arm Technology China) ;
bruce.richard...@intel.com; dev@dpdk.or
05/07/2019 10:37, jer...@marvell.com:
> Jerin Jacob (2):
> raw/octeontx2_dma: add build infra and device probe
> usertools: add octeontx2 DMA device binding
>
> Satha Rao (6):
> raw/octeontx2_dma: update probe function
> raw/octeontx2_dma: add device configuration
> raw/octeontx2_dma: ad
05/07/2019 04:41, Li, Xiaoyun:
> From: Thomas Monjalon
> >
> > This patch set adds support for Intel NTB device with Skylake platform.
> > It is a raw device for allowing two hosts to communicate with each other and
> > access the peer memory.
> >
> > This patch set also provides a simple example
> -Original Message-
> From: Medvedkin, Vladimir
> Sent: Friday, July 5, 2019 18:41
> To: Ruifeng Wang (Arm Technology China)
> Cc: Honnappa Nagarahalli ; Stephen
> Hemminger ; bruce.richard...@intel.com;
> dev@dpdk.org; Gavin Hu (Arm Technology China) ; nd
>
> Subject: Re: [dpdk-dev] [
This patchset adds multiple cores feature to compression perf tool.
All structures have been aligned and are consistent with crypto perf tool.
All test cases have constructor, runner and destructor and can use more
cores and compression devices at the same time.
v7 changes:
- rebase as patch fail
From: Tomasz Jozwiak
This patch adds template functions for multi-cores performance
version of compress-perf-tool
Signed-off-by: Tomasz Jozwiak
Signed-off-by: Tomasz Jozwiak
Acked-by: Artur Trybula
---
app/test-compress-perf/Makefile | 3 +-
app/test-compress-perf/comp_per
From: Tomasz Jozwiak
This patch adds a verification part to
compression-perf-tool as a separate test case, which can be
executed multi-threaded.
Signed-off-by: Tomasz Jozwiak
Signed-off-by: Tomasz Jozwiak
Acked-by: Artur Trybula
---
app/test-compress-perf/Makefile| 1 +
app
From: Tomasz Jozwiak
This patch adds a benchmark part to
compression-perf-tool as a separate test case, which can be
executed multi-threaded.
Also updates release notes.
Signed-off-by: Tomasz Jozwiak
Signed-off-by: Tomasz Jozwiak
Acked-by: Artur Trybula
---
app/test-compress-perf/Makefile
From: Tomasz Jozwiak
This patch adds --ptest option to make possible to choose
test case from command line.
Signed-off-by: Tomasz Jozwiak
Signed-off-by: Tomasz Jozwiak
Acked-by: Artur Trybula
---
app/test-compress-perf/comp_perf_options_parse.c | 32
1 file changed,
From: Tomasz Jozwiak
This patch updates dpdk-test-compress-perf documentation.
Signed-off-by: Tomasz Jozwiak
Acked-by: Artur Trybula
---
doc/guides/tools/comp_perf.rst | 34 +++---
1 file changed, 31 insertions(+), 3 deletions(-)
diff --git a/doc/guides/tools/comp
From: Tomasz Jozwiak
This patch adds a possibility to force controlled process termination
as a result of two signals: SIGTERM and SIGINT
Signed-off-by: Tomasz Jozwiak
Acked-by: Artur Trybula
---
app/test-compress-perf/comp_perf_options.h| 1 +
app/test-compress-perf/comp_perf_test_b
https://bugs.dpdk.org/show_bug.cgi?id=304
Bug ID: 304
Summary: [bnx2x_init] Initialization failed, stack notified
driver is NOT running!
Product: DPDK
Version: 19.05
Hardware: x86
OS: Linux
Statu
When using _mm_set_epi64() rather than _mm_set_epi64x() intrinsic, ICC
tries to use the x87 floating point registers, leading to warnings about
not properly clearing value when switching between x87 and SSE/AVX modes.
error #13203: No EMMS instruction before call to function
Fix this by u
From: Dilshod Urazov
Fixes: d299106e8e31 ("examples/ipsec-secgw: add IPsec sample application")
Cc: sta...@dpdk.org
Signed-off-by: Dilshod Urazov
Signed-off-by: Andrew Rybchenko
---
examples/ipsec-secgw/sa.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/examples/ipsec-se
25/06/2019 14:46, Akhil Goyal:
>
> >
> > This patch changes the key pointer data types in cipher, auth,
> > and aead xforms from "uint8_t *" to "const uint8_t *" for a
> > more intuitive and safe sessionn creation.
> >
> > Signed-off-by: Fan Zhang
> > Acked-by: Arek Kusztal
> > Acked-by: Akhil
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Bruce Richardson
> Sent: Friday, July 5, 2019 12:54 PM
> To: dev@dpdk.org
> Cc: Richardson, Bruce
> Subject: [dpdk-dev] [PATCH] raw/ioat: fix issue with icc build
>
> When using _mm_set_epi64() rather than _mm_set
On 05-Jul-19 12:54 PM, Bruce Richardson wrote:
When using _mm_set_epi64() rather than _mm_set_epi64x() intrinsic, ICC
tries to use the x87 floating point registers, leading to warnings about
not properly clearing value when switching between x87 and SSE/AVX modes.
error #13203: No EMMS i
05/07/2019 14:33, Burakov, Anatoly:
> On 05-Jul-19 12:54 PM, Bruce Richardson wrote:
> > When using _mm_set_epi64() rather than _mm_set_epi64x() intrinsic, ICC
> > tries to use the x87 floating point registers, leading to warnings about
> > not properly clearing value when switching between x87 and
Currently, the memory hotplug is locked automatically by all
memory-related _walk() functions, but sometimes locking the
memory subsystem outside of them is needed. There is no
public API to do that, so it creates a dependency on shared
memory config to be public. Fix this by introducing a new
API
This patchset removes the shared memory config from public
API, and replaces all usages of said config with new API
calls.
A lot of the patchset is a search-and-replace job and should
be pretty easy to review. The rest are pretty trivial EAL
changes.
v4:
- Rebase on top of latest master
- Squashe
Now that everything that has ever accessed the shared memory
config is doing so through the public API's, we can make it
internal. Since we're removing quite a few headers from
rte_eal_memconfig.h, we need to add them back in places
where this header is used.
This bumps the ABI, so also change all
Currently, locking/unlocking the TAILQ list requires direct
access to the shared memory config. Add an API to do the same,
and search-and-replace all usages.
Signed-off-by: Anatoly Burakov
Acked-by: Stephen Hemminger
---
lib/librte_acl/rte_acl.c | 18 ++--
lib/librt
Currently, in order to lock access to the mempool list, a direct
access to the shared memory structure is needed. Add an API to do
the same, and search-and-replace all usages.
Signed-off-by: Anatoly Burakov
Acked-by: Stephen Hemminger
---
lib/librte_eal/common/eal_common_mcfg.c | 28 +
Currently, the function to wait until config completion is
static inline for no reason. Move its implementation to
an EAL common file.
Signed-off-by: Anatoly Burakov
Acked-by: Stephen Hemminger
---
lib/librte_eal/common/eal_common_mcfg.c | 10 ++
lib/librte_eal/common/eal_memcfg.h
There is no reason to pack the memconfig structure, and doing so
gives out warnings in some static analyzers. Fix it by removing
the packed attributed.
Signed-off-by: Anatoly Burakov
Acked-by: Stephen Hemminger
---
lib/librte_eal/common/eal_memcfg.h | 2 +-
1 file changed, 1 insertion(+), 1 del
Currently, mcfg completion function exists in two independent
implementations doing the same thing, which is bug prone.
Unify the two functions and move them into one place.
Signed-off-by: Anatoly Burakov
Acked-by: Stephen Hemminger
---
lib/librte_eal/common/eal_common_mcfg.c | 14 +
Currently, each EAL will update internal/shared config in their
own way at init, resulting in needless duplication of code and
OS-dependent behavior. Move the functions to a common file and
add missing FreeBSD steps.
Signed-off-by: Anatoly Burakov
Acked-by: Stephen Hemminger
---
lib/librte_eal/
05/07/2019 11:48, Burakov, Anatoly:
> On 05-Jul-19 10:18 AM, David Marchand wrote:
> > Fixes: 552afc420a67 ("mem: add contig walk function")
> > Cc: sta...@dpdk.org
> >
> > Signed-off-by: David Marchand
>
> Acked-by: Anatoly Burakov
Applied, thanks
Currently, whenever timer library is initialized, the memory
is leaked because there is no telling when primary or secondary
processes get to use the state, and there is no way to
initialize/deinitialize timer library state without race
conditions [1] because the data itself must live in shared mem
Previous attempts [1] at fixing the resource leak have been
deemed unsuccessful because of limitations around what
can be done without breaking the ABI. Now that we've
broken the EAL ABI, we can fix this issue properly.
This patchset is adding a new lock API, as well as fixes the
actual issue.
Th
This patch fixes the missed "uint8_t *" to "const uint8_t *" xform
key data type change for mvsam driver.
Fixes: f3390532cf6a ("cryptodev: make xform key pointer constant")
Signed-off-by: Fan Zhang
---
drivers/crypto/mvsam/rte_mrvl_pmd.c | 44 ++---
drivers/crypt
Hi Fan,
>
> This patch fixes the missed "uint8_t *" to "const uint8_t *" xform
> key data type change for mvsam driver.
>
> Fixes: f3390532cf6a ("cryptodev: make xform key pointer constant")
>
> Signed-off-by: Fan Zhang
> ---
> drivers/crypto/mvsam/rte_mrvl_pmd.c | 44
> ++
Hi Liron,
Following patch need to be merged today as it is fixing a build issue for a
patch already merged.
Could you please review this patch? Sorry for a very short notice.
Thanks,
Akhil
> -Original Message-
> From: Fan Zhang
> Sent: Friday, July 5, 2019 6:54 PM
> To: dev@dpdk.org
>
пт, 5 июл. 2019 г. в 13:31, Medvedkin, Vladimir :
>
> Hi Stephen,
>
> On 28/06/2019 16:35, Stephen Hemminger wrote:
> > On Fri, 28 Jun 2019 15:16:30 +0100
> > "Medvedkin, Vladimir" wrote:
> >
> >> Hi Honnappa,
> >>
> >> On 28/06/2019 14:57, Honnappa Nagarahalli wrote:
> Hi all,
>
>
Hi,
>
>
> >
> > As a general remark consider writing all of the tbl entries including
> > tbl8 with atomic_store. Now "lpm->tbl8[j] = new_tbl8_entry;" is looks like
> >
> > 1e9: 44 88 9c 47 40 01 00mov
> > %r11b,0x2000140(%rdi,%rax,2) <-write first byte
> > 1f0: 02
> >
Hi Andrew, Dilshod
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Andrew Rybchenko
> Sent: Friday, July 5, 2019 1:18 PM
> To: Nicolau, Radu ; Akhil Goyal
>
> Cc: dev@dpdk.org; Dilshod Urazov ;
> sta...@dpdk.org
> Subject: [dpdk-dev] [PATCH] examples/ipsec-secg
Hi,
On Thu, Jul 04, 2019 at 06:29:25PM +0200, Thomas Monjalon wrote:
> 15/03/2019 16:27, Harman Kalra:
> > Since pdump uses SW rings to manage packets hence
> > pdump should use SW ring mempool for managing its
> > own copy of packets.
>
> I'm not sure to understand the reasoning.
> Reshma, Olivi
On Thu, Jul 04, 2019 at 04:23:02PM -0700, Yongseok Koh wrote:
> A tag is a transient data which can be used during flow match. This can be
> used to store match result from a previous table so that the same pattern
> need not be matched again on the next table. Even if outer header is
> decapsulate
Hi Akhil,
Thanks for the review, comments inline.
Regards,
Fan
> -Original Message-
> From: Akhil Goyal [mailto:akhil.go...@nxp.com]
> Sent: Friday, July 5, 2019 2:28 PM
> To: Zhang, Roy Fan ; dev@dpdk.org
> Subject: RE: [PATCH] crypto/mvsam: fix missed code change for mvsam
>
> Hi Fan,
- As "readlink -e" and "readlink -m" do not exist on freebsd,
use "readlink -f", it should not have any impact in these cases.
- "sed -ri" is invalid on freebsd and should be replaced by
"sed -ri=''"
- Use gmake instead of make.
This fixes the following command:
SYSDIR=/usr/src/sys ./devtool
1 - 100 of 160 matches
Mail list logo
